massaindustries commited on
Commit
e6d73e1
Β·
verified Β·
1 Parent(s): ace9366

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -19
README.md CHANGED
@@ -86,22 +86,9 @@ Not all prompts are equal. A factual recall question ("What is the capital of Fr
86
 
87
  **Brick** solves this by routing each query to the right model tier in real time. Complexity classification is one of several routing signals (alongside keyword matching, domain detection, and reasoning-depth estimation) that Brick uses to make sub-50ms routing decisions.
88
 
89
- ```
90
- User Query ──▢ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
91
- β”‚ Brick Router β”‚
92
- β”‚ β”‚
93
- β”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
94
- β”‚ β”‚ Complexity │──┼────▢│ easy β†’ Qwen 7B β”‚
95
- │ │ Extractor │ │ │ medium→ Llama 70B│
96
- β”‚ β”‚ (this model) β”‚ β”‚ β”‚ hard β†’ Claude β”‚
97
- β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
98
- β”‚ β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” β”‚
99
- β”‚ β”‚ Domain Det. β”‚ β”‚
100
- β”‚ β”‚ Keyword Match β”‚ β”‚
101
- β”‚ β”‚ Reasoning Est. β”‚ β”‚
102
- β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β”‚
103
- β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
104
- ```
105
 
106
  ## Model Details
107
 
@@ -257,8 +244,8 @@ model_pools:
257
 
258
  ### ⚠️ Out-of-Scope Uses
259
  - **Content moderation or safety filtering** β€” this model classifies cognitive difficulty, not content safety
260
- - **Non-English queries** β€” trained on English data only; accuracy degrades significantly on other languages
261
- - **Direct use as a chatbot or generative model** β€” this is a classification adapter, not a generative model
262
 
263
  ## Limitations
264
 
@@ -315,7 +302,7 @@ Regolo.ai is committed to sustainable AI. This model was trained on GPU infrastr
315
 
316
  ## About Regolo.ai
317
 
318
- [Regolo.ai](https://regolo.ai) is the EU-sovereign LLM inference platform built on [Seeweb](https://www.seeweb.it/) infrastructure. We provide zero-data-retention, GDPR-native AI inference for enterprises that need privacy, compliance, and performance β€” all from European data centers powered by renewable energy.
319
 
320
  **Brick** is our open-source semantic routing system that intelligently distributes queries across model pools, optimizing for cost, latency, and quality.
321
 
 
86
 
87
  **Brick** solves this by routing each query to the right model tier in real time. Complexity classification is one of several routing signals (alongside keyword matching, domain detection, and reasoning-depth estimation) that Brick uses to make sub-50ms routing decisions.
88
 
89
+
90
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/66e9a629df006ca4588b82bd/ZoRBcn8rD8sTEHdkiczOO.png" alt="brick_router" width="800">
91
+
 
 
 
 
 
 
 
 
 
 
 
 
 
92
 
93
  ## Model Details
94
 
 
244
 
245
  ### ⚠️ Out-of-Scope Uses
246
  - **Content moderation or safety filtering** β€” this model classifies cognitive difficulty, not content safety
247
+ - **Non-English queries** trained on English data only; accuracy degrades significantly on other languages
248
+ - **Direct use as a chatbot or generative model** this is a classification adapter, not a generative model
249
 
250
  ## Limitations
251
 
 
302
 
303
  ## About Regolo.ai
304
 
305
+ [Regolo.ai](https://regolo.ai) is the EU-sovereign LLM inference platform built on [Seeweb](https://www.seeweb.it/) infrastructure. We provide zero-data-retention, GDPR-native AI inference for enterprises that need privacy, compliance, and performance all from European data centers powered by renewable energy.
306
 
307
  **Brick** is our open-source semantic routing system that intelligently distributes queries across model pools, optimizing for cost, latency, and quality.
308